feat: make LLM timeout configurable (default 5min)
CI / test (pull_request) Successful in 13s
CI / review (gpt-5, sonnet, SONNET_REVIEW_TOKEN) (pull_request) Successful in 1m6s
CI / review (gpt-5-mini, gpt, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m14s

New flag: --llm-timeout / LLM_TIMEOUT (seconds, default 300)
New builder: llmClient.WithTimeout(duration)
Composite action: new timeout input

Keeps 5 minutes as the sensible default but allows tuning for
larger repos or slower models.
This commit is contained in:
Rodin
2026-05-01 13:04:00 -07:00
parent 401e94d3e4
commit 1da61e514d
3 changed files with 38 additions and 1 deletions
+6
View File
@@ -32,6 +32,12 @@ func NewClient(baseURL, apiKey, model string) *Client {
}
// WithTemperature sets the temperature for LLM requests (0 = omit, uses server default).
// WithTimeout sets the HTTP request timeout for LLM calls (default 5 minutes).
func (c *Client) WithTimeout(d time.Duration) *Client {
c.http.Timeout = d
return c
}
func (c *Client) WithTemperature(t float64) *Client {
c.temperature = t
return c